#

selective-decode

Here is 1 public repository matching this topic...

latent-gate

KathanModh259 / latent-gate

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

python ai computer-vision python3 gemini openai embedding claude multimodal vision-language cost-reduction local-llm ollama llm-pipeline prompt-compression token-optimization selective-decode vl-jepa api-cost

Updated Jun 17, 2026
Python

Improve this page

Add a description, image, and links to the selective-decode topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the selective-decode topic, visit your repo's landing page and select "manage topics."